Script to video
Creates a project and generates a narrated video from a prompt or script. Returns immediately with a workflow run id; poll or subscribe to webhooks for completion.
Request body
The narration script, used verbatim. This exact text is narrated and turned into a video — it is not rewritten or expanded.
How quickly visuals change. FAST shows more, shorter shots; SLOW holds each visual longer. Defaults to MEDIUM.
AI generation quality tier, shared across every generative feature (image, video, text, and so on). LOW is fastest and cheapest, STANDARD balances quality and cost, HIGH is higher quality, and MAX is the highest quality.
When a request omits the quality field, VideoGen falls back to your account's Default AI quality for that feature, which you can change at Account settings. Not every feature supports every tier; unsupported tiers are rejected with an error (see each field's description).
Output language as a BCP-47 code (e.g. en, es, fr). Defaults to English.
Catalog displayName (e.g. Matilda) or voice id from GET /v1/resources/tts-voices (e.g. vg_voic_...). A default voice is used when omitted. Any voice may be used here, including voices where supportsDirectToolExecution is false.
Speech rate multiplier, between 0.5 (half speed) and 2 (double speed). Defaults to the voice's default speed.
Recommended. Optional id of a built-in stock actor or an ACTOR entity (e.g. vg_enti_...) with an image reference. When set, narration is delivered by that actor avatar. Omit or pass null for voiceover without an avatar.
AI generation quality tier, shared across every generative feature (image, video, text, and so on). LOW is fastest and cheapest, STANDARD balances quality and cost, HIGH is higher quality, and MAX is the highest quality.
When a request omits the quality field, VideoGen falls back to your account's Default AI quality for that feature, which you can change at Account settings. Not every feature supports every tier; unsupported tiers are rejected with an error (see each field's description).
Optional file ids of images or videos to feature as b-roll (e.g. ["vg_file_..."]). Upload files first via POST /v1/files/upload. Only image and video files are accepted.
Optional production notes for the AI that builds the video — visual direction that should not appear in the spoken narration (e.g. on-screen code or text to display, specific b-roll to feature, or scene-by-scene staging). Never spoken; keep the narration itself in script.
When true, the video's generated OUTPUT files (AI images, video clips, voiceover audio, avatars) are created as temporary: guaranteed available for 24 hours, after which they may be archived and later deleted. This also covers files produced by post-build remix actions (e.g. generated background music, image-to-video conversions). Use this when your integration downloads or re-hosts the results itself and does not need VideoGen to retain them. The project and its metadata are unaffected. Defaults to false.
When true, generated files are hidden from the VideoGen Media page by default. They remain accessible through the API. Defaults to false.
Response
Workflow run accepted.
Opaque workflow run id (e.g. vg_work_...).
Id of the project created for this workflow run (e.g. vg_proj_...).
Deep link to open this project in the VideoGen web editor. Not required for an API-only integration: store projectId and use the Projects API (export, remix, metadata). Use projectUrl when a person should open the project in the app to review or edit it manually. The project is visible only to members of your team and any project collaborators, the same access model as a project created in the dashboard.
Opaque remix action ids (e.g. vg_rmix_...), one per remixActions entry in request order. Empty when no remix actions were requested. Each runs after the video is built; poll GET /v1/projects/{projectId}/remix-actions.
Changes
No recorded changes to this endpoint across all 1 revision of this API.